Business processing method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a business processing method, electronic equipment, a storage medium and a program product, and relates to the field of financial science and technology or other related fields. The method comprises the following steps: collecting audio information of a user, and extracting voiceprint information of the user from the audio information; identifying whether the user is a historical user with a business handling record according to the voiceprint information; and under the condition that the user is a historical user, determining a corresponding service processing strategy according to the current time, and executing a corresponding service processing operation according to the service processing strategy. According to the method provided by the invention, when the user enters the bank outlet for business handling, whether the user is the historical user can be quickly identified, the corresponding business processing strategy is determined for the historical user, and the corresponding business processing operation is executed, so that the business handling efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other related fields, and in particular to a business processing method, electronic device, storage medium and program product. Background Art

[0002] Bank branches provide a wide variety of services and users have different needs. Therefore, it is difficult to quickly determine users' business needs during the business process, which can easily lead to users being dissatisfied due to long waiting times or unclear business processes.

[0003] In the existing banking business processing methods, the business processing efficiency is low because the processing personnel of the bank branch cannot quickly determine the user's business processing needs and process the business in a timely manner. Summary of the invention

[0004] The present application provides a business processing method, device, equipment, storage medium and product to solve the technical problem of low business processing efficiency.

[0005] In a first aspect, the present application provides a business processing method, including:

[0006] Collecting audio information of a user, and extracting voiceprint information of the user from the audio information;

[0007] Identify whether the user is a historical user with a business handling record according to the voiceprint information;

[0008] In the case where the user is a historical user, a corresponding service processing strategy is determined according to the current time, and a corresponding service processing operation is performed according to the service processing strategy.

[0009] In a second aspect, the present application provides a service processing device, including:

[0010] An extraction module, used to collect audio information of a user and extract the voiceprint information of the user from the audio information;

[0011] An identification module, used to determine whether the user is a historical user with a business handling record according to the voiceprint information;

[0012] The execution module is used to determine the corresponding business processing strategy according to the current time when the user is a historical user, and execute the corresponding business processing operation according to the business processing strategy.

[0013] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0014] The memory stores computer-executable instructions;

[0015] The processor executes the computer-executable instructions stored in the memory to implement the method according to the first aspect.

[0016] In a third aspect, the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0017] In a fourth aspect, the present application provides a computer program product, characterized in that it includes a computer program, and when the computer program is executed by a processor, it implements the method described in the first aspect.

[0018] The business processing method, electronic device, storage medium and program product provided by the present application collect audio information after the user enters a bank branch, so as to identify whether the user is a historical user with a business processing record through voiceprint, and if the user is a historical user, determine the corresponding business processing strategy according to the current time, so as to perform the corresponding business processing operation according to the business processing strategy. The method of the present application can quickly identify whether the user is a historical user when the user enters a bank branch to handle business, determine the corresponding business processing strategy for the historical user, and perform the corresponding business processing operation, thereby improving the efficiency of business handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] Figure 1 A flowchart of a business processing method provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of a process for executing a business processing operation provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of a method for extracting a user's voiceprint information provided in an embodiment of the present application;

[0023] Figure 4 A flowchart of a method for identifying a user based on voiceprint information provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of the structure of a service processing device provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0026] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0028] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0029] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0030] It should be noted that the business processing methods, devices, equipment, storage media and program products provided in this application can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application fields of the business processing methods, devices, equipment, storage media and program products in this application are not limited.

[0031] In the existing banking business processing methods, the business processing efficiency is low because the processing personnel of the bank branch cannot quickly determine the user's business processing needs and process the business in a timely manner.

[0032] In view of this, the present application provides a business processing method, which collects audio information after the user enters a bank branch to determine whether the user is a historical user with a business processing record, and determines the corresponding business processing strategy according to the current time to perform the corresponding business processing operation. The method of the present application can quickly identify whether the user is a historical user when the user enters a bank branch to handle business, and determine the corresponding business processing strategy for the historical user, and perform the corresponding business processing operation, thereby improving the efficiency of business handling.

[0033] It should be understood that the execution subject of the method of the embodiment of the present application can be a business processing system. It should be noted that the business processing system can be deployed separately on an electronic device in any environment (for example, deployed separately on an edge server in an edge environment), or all deployed in a cloud environment, or distributedly deployed in different environments.

[0034] For example, the business processing system can be logically divided into multiple parts, each with different functions. The parts in the business processing system can be deployed in any two or three of the electronic device (located on the user side), the edge environment, and the cloud environment. The edge environment is an environment that includes a collection of edge electronic devices that are close to the electronic device. The edge electronic devices include: edge servers, edge stations with computing power, etc. The various parts of the business processing system deployed in different environments or devices work together to realize the functions of the business processing system.

[0035] It should be understood that this application does not restrictively divide which parts of the business processing system are deployed in what specific environment. In actual application, it can be adaptively deployed according to the computing power of the electronic device, the resource usage of the edge environment and the cloud environment, or the specific application requirements.

[0036] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0037] Figure 1 Schematic diagram of a process flow of a business processing method provided in an embodiment of the present application. Figure 1 As shown, the business processing method of the present application specifically includes the following steps:

[0038] S101. Collecting audio information of a user, and extracting voiceprint information of the user from the audio information.

[0039] Audio information refers to information captured by a sound recording device, such as audio recorded by a microphone. Audio information includes user voice and environmental noise.

[0040] Voiceprint information is the voiceprint feature of the user's voice in the audio information, and can be used to identify or verify the user's identity based on the voiceprint information.

[0041] One possible implementation method is to collect audio information based on any terminal with a microphone device in the lobby of a bank branch. For example, the user's audio information can be collected based on a robot. In this method, multiple robots can be deployed in the lobby of a bank branch. Each robot can patrol its own area and interact with the user by voice during the patrol. For example, the robot can actively ask the user to request permission to record the user's audio information. After the user confirms the authorization to collect audio information, the user's audio information can be recorded based on the microphone array deployed on the robot. For example, a consultation desk can also be set up in the lobby of a bank. During the user's consultation, the user can request permission to record the user's audio information. After the user confirms the authorization to collect audio information, the user's audio information can be recorded.

[0042] After collecting the user's audio information, the user's voiceprint information is extracted from the audio information. One possible implementation method is to preprocess the user's audio information, such as applying filtering technology to remove background noise. Feature extraction and feature selection are performed based on the audio information after signal preprocessing, such as obtaining feature vectors through relevant feature extraction methods, and using dimensionality reduction methods in related technologies to retain features with high recognition power.

[0043] One possible implementation method of extracting the user's voiceprint information from the audio information is to extract the user's voiceprint information from the audio information based on the feature extraction model in the prior art. The audio information after signal preprocessing is input into the feature extraction model, and the feature extraction model performs signal conversion on the preprocessed audio information to obtain an audio spectrum, and processes the audio spectrum through a filter bank, calculates the output of each filter, and obtains the user's voiceprint information.

[0044] Optionally, the user's audio information may be collected periodically. Taking the collection of the user's audio information through a robot as an example, if the user continuously interacts with the robot by voice, the user's audio information may be recorded once every 1 minute.

[0045] S102: Identify whether the user is a historical user with a business handling record based on the voiceprint information.

[0046] Historical users are users who have handled business in the bank. Each historical user has a corresponding business handling record, which is used to record the relevant content of the business handled by the user.

[0047] In a possible implementation, a historical user voiceprint library is stored in the business processing system, and the user's voiceprint information is compared with the voiceprint information in the historical user voiceprint library, and the similarity between the user's voiceprint information and each voiceprint information in the historical user voiceprint library is calculated, such as Euclidean distance or cosine similarity, etc. When the similarity between the user's voiceprint information and any voiceprint information in the historical user voiceprint library is greater than a preset threshold, the user is confirmed to be a historical user with a business processing record. When the user is confirmed to be a historical user with a business processing record, the historical user corresponding to the voiceprint information with the greatest similarity to the user's voiceprint information in the historical user voiceprint library is selected and confirmed to be the same user.

[0048] One possible implementation method is to identify whether the user is a historical user with a business handling record based on a pre-trained voiceprint recognition model. In this method, the pre-trained voiceprint recognition model is trained based on the voiceprint information of the historical user, and can identify whether the voiceprint information matches the voiceprint information of the historical user. The user's voiceprint information is input into the voiceprint recognition model, and the voiceprint recognition model can output whether the user of the voiceprint information matches the historical user with a business handling record, and confirm the relevant information of the matched historical user, and the relevant information of the historical user can be, for example, the identifier of the historical user.

[0049] S103: When the user is a historical user, determine a corresponding service processing strategy according to the current time, and perform a corresponding service processing operation according to the service processing strategy.

[0050] The business processing strategy may be, for example, a robot processing strategy or a manual processing strategy. The robot processing strategy may be a strategy for processing business by controlling a robot, and the manual processing strategy may be a strategy for processing business by a processing person. Optionally, 9:00 to 18:00 from Monday to Friday may be the first time period, the time periods other than 9:00 to 18:00 from Monday to Friday may be the second time period, 9:00 to 18:00 from Saturday to Sunday may be the third time period, and 9:00 to 18:00 from Saturday to Sunday may be the fourth time period, and corresponding business processing strategies may be preset for each time period.

[0051] The service processing operation is an operation of performing service processing according to the service processing strategy. Taking the robot processing strategy as an example, the service processing operation may include controlling the robot to move to the location of the user.

[0052] In the case where the user is a historical user, the corresponding service processing strategy is determined according to the current time, and the corresponding service processing operation is performed according to the service processing strategy. The corresponding service processing strategy is determined according to the current time, and the time period can be divided into quarters, months and / or moments, and the corresponding service processing strategy is determined based on each time period.

[0053] One possible implementation method is to divide the time periods according to the daily time as an example. For example, the daily time is divided into two time periods, 9:00 to 18:00 is the first time period, and the other time periods except 9:00 to 18:00 are the second time period. In this method, the corresponding business processing strategies can be preset based on the two time periods. For example, the business processing strategy corresponding to the first time period from 9:00 to 18:00 is the manual processing strategy, and the business processing strategy corresponding to the other time periods except 9:00 to 18:00 is the robot processing strategy. Furthermore, the corresponding business processing operation is executed based on the business handling record combined with the business processing strategy.

[0054] One possible implementation method is to train a model based on historical business processing records, classify and mark historical business processing records according to the divided time periods, train a model based on the marked time periods and the business processing strategies of historical business processing records, and pre-generate corresponding business processing strategies for each time period based on the trained model. In this method, the business processing strategy corresponding to the corresponding time period is determined according to the current time, and the corresponding business processing operation is executed according to the business processing strategy.

[0055] One possible implementation method is to train a model based on historical business processing records, classify and mark historical business processing records according to the divided time periods, train a model based on the marked time periods and the business processing strategies of historical business processing records, and generate corresponding business processing strategies for each time period based on the trained model. In this method, the current time and the user's business processing record history are input into the trained model to obtain the corresponding business processing strategy, and the corresponding business processing operation is executed according to the business processing strategy.

[0056] The business processing method provided in this embodiment collects audio information after the user enters a bank branch, so as to identify whether the user is a historical user with a business processing record through voiceprint, and if the user is a historical user, determine the corresponding business processing strategy according to the current time, so as to perform the corresponding business processing operation according to the business processing strategy. The method of the present application can quickly identify whether the user is a historical user when the user enters a bank branch to handle business, determine the corresponding business processing strategy for the historical user, and perform the corresponding business processing operation, thereby improving the efficiency of business handling.

[0057] The following is an example of how to determine the corresponding business processing strategy according to the current time in the business processing method of the present application, and perform the corresponding business processing operation according to the business processing strategy. For example, the following is an example in which the execution subject of the method of the embodiment of the present application is a business processing system, the business processing system is distributedly deployed in the robot in the lobby of the bank branch, and the server in the bank branch, and the current time can be in the first time period, the second time period, or the third time period.

[0058] The first time period, the second time period or the third time period is three divided time periods. For example, according to the time, 9:00 to 18:00 can be the first time period, 18:00 to 20:00 can be the second time period, and 0:00 to 9:00 and 20:00 to 24:00 can be the third time period.

[0059] Figure 2 1 is a flow chart of a business processing operation provided in an embodiment of the present application. Taking the three time periods divided above as an example, Figure 2 As shown, first, step S201 may be executed to determine the time period to which the current time belongs based on the current time.

[0060] A possible implementation method, when the current time is in the first time period, may specifically include the following steps:

[0061] S202: Determine that the business processing strategy is a manual processing strategy.

[0062] The manual processing strategy is a strategy for bank branch staff to process business. When the current time is in the first time period, the business processing strategy is determined to be the manual processing strategy.

[0063] S203: Determine the historical processing personnel according to the user's business handling record, and send a prompt message to the terminal of the historical processing personnel.

[0064] The historical processing personnel are processing personnel corresponding to the historical business recorded in the business processing record of the user. The prompt information is used to prompt the historical processing personnel with relevant information of the user to be received, such as the user's location and business processing record.

[0065] When the business processing strategy is a manual processing strategy, the historical processing personnel are determined according to the user's business processing record, and a prompt message is sent to the terminal of the historical processing personnel, the prompt information including the user's location and business processing record.

[0066] In this mode, taking the three time periods divided above as an example, when the current time is between 9:00 and 18:00, i.e., the first time period, the business processing strategy is determined to be a manual processing strategy, the historical processing personnel are determined based on the user's business processing records, and a prompt message is sent to the terminal of the historical processing personnel, which can be, for example, a personal computer or mobile phone of the historical processing personnel. Taking the example of collecting the user's audio information through a robot, the robot can also determine the user's location information and send the user's location information to the server in the bank branch. After determining the historical processing personnel, the server in the bank branch sends the user's business processing record and the user's location to the terminal of the historical processing personnel in any form. For example, a text message can be sent to the mobile phone of the historical processing personnel in the form of a text message.

[0067] Optionally, after sending the prompt message to the terminal of the history processing personnel, the new prompt message can also be deleted in response to the confirmation instruction of the prompt message if the new prompt message is the same as the confirmed prompt message. The new prompt message is determined based on the user's new audio information.

[0068] In the case of collecting the user's audio information multiple times, the business processing record determined based on the user's new audio information is the same as the business processing record determined based on the previous audio information. In this state, the corresponding historical processing personnel is the same person, and the prompt message is the same, and the prompt message can continue to be sent to the terminal of the historical processing personnel. Optionally, the historical processing personnel can perform a confirmation operation. For example, the prompt message is sent to the mobile phone of the historical processing personnel via SMS. The historical processing personnel can reply to the SMS to confirm the receipt of the prompt message. In this way, in response to the confirmation instruction of the prompt message, if the new prompt message is the same as the confirmed prompt message, the new prompt message can be deleted, that is, the new prompt message is not sent to the terminal of the historical processing personnel.

[0069] A possible implementation method, when the current time is in the second time period, may specifically include the following steps:

[0070] S204: Determine that the business processing strategy is a robot processing strategy.

[0071] The robot processing strategy is a strategy for processing business through a robot. When the current time is in the second time period, the business processing strategy is determined to be the robot processing strategy.

[0072] S205: Control the robot to move toward the user and output user greeting information.

[0073] User greeting information is voice information used to control the robot to perform voice interaction with the user.

[0074] When the service processing strategy is a robot processing strategy, the robot is controlled to move toward the user and output user greeting information.

[0075] In this mode, taking the three time periods divided above as an example, when the current time is between 18:00 and 20:00, i.e., the second time period, the business processing strategy is determined to be the robot processing strategy, and the robot is controlled to move toward the user. In this mode, the robot can, for example, acquire images through its own image acquisition unit, and based on the image processing method in the related art, identify the user's location, and move toward the user's location. After approaching the user, the robot outputs user greeting information, such as information asking about the user's business needs.

[0076] Optionally, in this mode, the robot can respond to the user's needs, interact with the user by voice to answer questions, and provide business self-service, that is, the user can handle related business by himself. Optionally, the robot can also provide manual service functions. When the user requires manual service, the corresponding manual service personnel can be determined according to the user's business handling record, and the robot can talk to the corresponding manual service personnel through voice, so that the user and the manual service personnel can communicate remotely.

[0077] A possible implementation method, when the current time is in the third time period, may specifically include the following steps:

[0078] S206: Determine the business processing strategy as a monitoring strategy.

[0079] The monitoring strategy is a strategy for monitoring the health status of the user through the robot. When the current time is in the third time period, the service processing strategy is determined to be the monitoring strategy.

[0080] S207: Control the robot to move toward the user and obtain the image of the user.

[0081] S208: When the user's health status is abnormal, a rescue request message is sent to the rescue platform.

[0082] The rescue request information is information for requesting rescue help, and the rescue request information includes the user's location, so that the user's location can be confirmed by requesting the rescue information.

[0083] When the business processing strategy is the monitoring strategy, the robot can be controlled to move toward the user and obtain the user's image. The user's health status is determined based on the image. If the user's health status is abnormal, a rescue request message is sent to the rescue platform, and the rescue request message includes the user's location.

[0084] In this mode, taking the three time periods divided above as an example, when the current time is in the time period from 0:00 to 9:00 or the time period from 20:00 to 24:00, that is, the third time period, the business processing strategy is determined to be the monitoring strategy, and the robot is controlled to move toward the user. In this mode, the robot can, for example, obtain images through its own image acquisition unit, and based on the image processing method in the relevant technology, identify the user's location, and move to the user's location. After approaching the user, the robot can continue to obtain images of the user and judge the user's health status based on the image. Among them, judging the user's health status based on the image can, for example, be based on the body posture analysis method in the relevant technology. The body posture analysis method in the relevant technology can identify the body posture of the person in the image, and judge whether it is an abnormal state based on the body posture of the person.

[0085] When it is determined based on the image that the user's health status is abnormal, a rescue request message is sent to the rescue platform. For example, the robot can talk to the rescue platform and control the robot to inform the rescue platform of the user's location through voice.

[0086] Optionally, after the robot moves to the user's location, it can continue to communicate with the user in a time period. If the user does not respond within a continuous time period, the robot further collects images of the user, and sends a rescue request to the rescue platform when the user's health status is judged to be abnormal based on the image. Optionally, the robot can also respond to the user's rescue request instruction. For example, the user expresses information related to the request for rescue to the robot through voice, and the robot responds to the user's rescue request instruction and sends a rescue request to the rescue platform. After the robot responds to the user's rescue request instruction, it can also optionally collect images of the user. In this way, when the user's health status is judged to be abnormal based on the image, a rescue request is sent to the rescue platform.

[0087] The business processing method provided in this embodiment collects audio information after the user enters a bank branch, so as to identify whether the user is a historical user with a business processing record through voiceprint, and if the user is a historical user, determine the corresponding business processing strategy according to the current time, so as to perform the corresponding business processing operation according to the business processing strategy. The method of the present application can quickly identify whether the user is a historical user when the user enters a bank branch to handle business, determine the corresponding business processing strategy for the historical user, and perform the corresponding business processing operation, thereby improving the efficiency of business handling.

[0088] The following describes how to extract the user's voiceprint information from the audio information in the business processing method of this application, and identify whether the user is a historical user with a business processing record based on the voiceprint information.

[0089] Figure 3 The following is a flow chart of a method for extracting a user's voiceprint information provided in an embodiment of the present application. Exemplarily, extracting a user's voiceprint information from audio information includes:

[0090] S301. Determine the time-frequency masking of a speech signal in audio information, and determine the power spectrum of the speech signal according to the time-frequency masking of the speech signal.

[0091] The audio information includes voice signals and noise signals. The voice signal includes the user's voiceprint features, and the noise signal is an interference signal.

[0092] Time-frequency masking is a signal processing technology that adjusts the gain of a signal at different time and frequency components through a masking matrix. The power spectrum of a signal can be obtained based on the time-frequency masking of the signal.

[0093] For example, the model is used to estimate the time-frequency masking of a speech signal. Exemplarily, a preliminary power spectrum is obtained through Fourier transform based on audio information, the preliminary power spectrum is input into the model, and a masking matrix of the speech signal output by the model is obtained. The masking matrix of the speech signal is applied to the preliminary power spectrum to determine the power spectrum of the speech signal.

[0094] S302: Determine the time-frequency masking of the noise signal in the audio information, and determine the power spectrum of the noise signal according to the time-frequency masking of the noise signal.

[0095] For example, the model is used to estimate the time-frequency masking of the noise signal. For example, a preliminary power spectrum is obtained through Fourier transform based on the audio information, the preliminary power spectrum is input into the model, and the masking matrix of the noise signal output by the model is obtained. The masking matrix of the noise signal is applied to the preliminary power spectrum to determine the power spectrum of the noise signal.

[0096] S303: Separate the speech signal from the noise signal according to the power spectrum of the speech signal and the power spectrum of the noise signal, and perform enhancement processing on the separated speech signal to obtain voiceprint information.

[0097] For example, according to the power spectrum of the speech signal and the power spectrum of the noise signal, the speech signal is separated from the noise signal, and the speech signal is enhanced through the generalized extreme value (GEV) beamformer and blind analysis normalization (BAN) to maximize the output signal-to-noise ratio and obtain the enhanced speech signal, i.e., voiceprint information.

[0098] Figure 4The following is a flow chart of a method for identifying a user based on voiceprint information provided in an embodiment of the present application. Exemplarily, identifying whether a user is a historical user with a business handling record based on voiceprint information includes:

[0099] S401: Extract voiceprint features from voiceprint information.

[0100] Extract voiceprint information from the voiceprint information, for example, extract filter bank features (FBANK) features.

[0101] S402: According to the voiceprint features and the historical user voiceprint library, a voiceprint recognition model is used to identify whether the voiceprint information is the voiceprint information in the historical user voiceprint library.

[0102] The historical user voiceprint database includes the voiceprint information of users with business handling records. The voiceprint recognition model can be pre-trained based on the voiceprint information in the historical user voiceprint database. For example, a triple (anchor, positive, negative) is generated through the historical user voiceprint database, where anchor is an anchor point, representing the voiceprint information of a user, positive is a positive sample, representing the voiceprint information from the same user as the anchor point, and negative is a negative sample, representing the voiceprint information from a different user than the anchor point. The core idea of ​​triplet training is to use triplet loss to optimize the model so that the voiceprint information features of the same user are closer in the feature space, while the voiceprint information features of different users are farther away. For example, the similarity between the anchor and the positive, as well as the similarity between the anchor and the negative is calculated. During the training process, the similarity between the anchor and the positive is maximized, and the similarity between the anchor and the negative is minimized. The similarity can be calculated, for example, by Euclidean distance similarity. Based on the trained voiceprint recognition model, voiceprint information can be input, and the model performs voiceprint recognition on the input voiceprint information, and outputs the result of whether the voiceprint information is the voiceprint information in the historical user voiceprint library.

[0103] S403: When the voiceprint information is in a historical user voiceprint database, determine that the user is a historical user.

[0104] Optionally, the business processing method of the present application may also display the business processing record through a display device, and delete the business processing record corresponding to the business processing operation in response to a completion instruction of the business processing operation.

[0105] The business processing record includes the user, current time and progress of the business processing operation. The display device can be any device that can display data. For example, taking the execution subject of the business processing method as a server of a bank branch as an example, the display device can be any screen that is connected to the server in communication.

[0106] In this mode, the user, current time and progress of the business processing operation are displayed on the screen by any visualization method. The user can be represented by the user's identification. For example, after sending a prompt message to the terminal of the history processing personnel, the user's serial number, current time and progress of the business processing operation are displayed as prompt information has been sent.

[0107] In response to the completion instruction of the business processing operation, the business processing record corresponding to the business processing operation is deleted, that is, the display of the business processing record on the screen is cancelled.

[0108] By displaying the business processing records on a display device, the progress of the business processing operation can be displayed in real time. By visualizing the progress of the business processing operation, the business processing operations of the bank branch can be quickly analyzed. Furthermore, for businesses whose progress of business processing operations has not been updated for a long time, timely intervention can be carried out to improve business processing efficiency.

[0109] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0110] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0111] The above is a description of the method embodiment of the present application. The following is a description of the business processing device provided in the embodiment of the present application.

[0112] Figure 5A schematic diagram of the structure of a service processing device provided in an embodiment of the present application. Figure 5 As shown, the device may include, for example: an extraction module 501, an identification module 502, and an execution module 503. Optionally, a display device 504 may also be included.

[0113] An extraction module 501 is used to collect audio information of a user and extract the voiceprint information of the user from the audio information;

[0114] Identification module 502, used to determine whether the user is a historical user with a business handling record according to the voiceprint information;

[0115] The execution module 503 is used to determine the corresponding service processing strategy according to the current time when the user is a historical user, and execute the corresponding service processing operation according to the service processing strategy.

[0116] In one possible implementation, the execution module 503 is specifically used to determine that the business processing strategy is a manual processing strategy when the current time is in the first time period; when the business processing strategy is the manual processing strategy, determine the historical processing personnel based on the user's business processing record, and send a prompt message to the terminal of the historical processing personnel, wherein the prompt information includes the user's location and the business processing record.

[0117] A possible implementation method is that after sending the prompt message to the terminal of the historical processing personnel, the execution module 503 is also used to respond to the confirmation instruction of the prompt message, and if the new prompt message is the same as the confirmed prompt message, delete the new prompt message, and the new prompt message is determined based on the new audio information of the user.

[0118] In a possible implementation, the execution module 503 is specifically used to determine that the business processing strategy is a robot processing strategy when the current time is in the second time period; when the business processing strategy is the robot processing strategy, control the robot to move toward the user and output user greeting information.

[0119] In a possible implementation, the execution module 503 is specifically configured to, when the current time is in the third time period, determine that the service processing strategy is a guardianship strategy; when the service processing strategy is the guardianship strategy, control the robot to move toward the user and acquire an image of the user;

[0120] The health status of the user is determined based on the image, and when the health status of the user is abnormal, a rescue request message is sent to a rescue platform, wherein the rescue request message includes the location of the user.

[0121] In a possible implementation, the extraction module 501 is specifically used to determine the time-frequency masking of the speech signal in the audio information, and determine the power spectrum of the speech signal according to the time-frequency masking of the speech signal; determine the time-frequency masking of the noise signal in the audio information, and determine the power spectrum of the noise signal according to the time-frequency masking of the noise signal; separate the speech signal from the noise signal according to the power spectrum of the speech signal and the power spectrum of the noise signal, and enhance the separated speech signal to obtain the voiceprint information.

[0122] In one possible implementation, the identification module 502 is specifically used to extract voiceprint features from the voiceprint information; based on the voiceprint features and the historical user voiceprint library, identify through a voiceprint recognition model whether the voiceprint information is the voiceprint information in the historical user voiceprint library, and the historical user voiceprint library includes the voiceprint information of users with business processing records; when the voiceprint information is the voiceprint information in the historical user voiceprint library, determine that the user is a historical user.

[0123] In one possible implementation, the display device 504 is specifically used to display the business processing record through the display device, and the business processing record includes the user, the current time and the progress of the business processing operation; in response to the completion instruction of the business processing operation, the business processing record corresponding to the business processing operation is deleted.

[0124] The device provided in the embodiment of the present application can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0125] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0126] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device may include: at least one processor 601 and a memory 602 .

[0127] The memory 602 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.

[0128] The memory 602 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0129] The processor 601 is used to execute the computer-executable instructions stored in the memory 602 to implement the method of the aforementioned method embodiment. The processor 601 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0130] Optionally, the electronic device may further include a communication interface 603. In specific implementation, if the communication interface 603, the memory 602 and the processor 601 are implemented independently, the communication interface 603, the memory 602 and the processor 601 may be interconnected via a bus and communicate with each other.

[0131] Optionally, in a specific implementation, if the communication interface 603, the memory 602 and the processor 601 are integrated on a chip, the communication interface 603, the memory 602 and the processor 601 can communicate through an internal interface.

[0132] The present application also provides a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes. Specifically, the computer-readable storage medium stores program instructions, and the program instructions are used to implement the actions of the above-mentioned method implementation method.

[0133] The present application also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of the electronic device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the electronic device implements the actions of the above method implementation.

[0134] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0135] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc.

[0136] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0137] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0139] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A business processing method, characterized in that: include: Collecting audio information of a user, and extracting voiceprint information of the user from the audio information; Identify whether the user is a historical user with a business handling record according to the voiceprint information; In the case where the user is a historical user, a corresponding service processing strategy is determined according to the current time, and a corresponding service processing operation is performed according to the service processing strategy.

2. The method according to claim 1, characterized in that The determining a corresponding service processing strategy according to the current time, and performing a corresponding service processing operation according to the service processing strategy, includes: When the current time is in the first time period, determining that the service processing strategy is a manual processing strategy; In the case where the business processing strategy is a manual processing strategy, the historical processing personnel are determined according to the business processing record of the user, and a prompt message is sent to the terminal of the historical processing personnel, wherein the prompt information includes the location of the user and the business processing record.

3. The method according to claim 2, characterized in that After sending the prompt message to the terminal of the history processing personnel, the method further includes: In response to a confirmation instruction of the prompt message, if the new prompt message is the same as the confirmed prompt message, the new prompt message is deleted, and the new prompt message is determined based on the new audio information of the user.

4. The method according to claim 1, characterized in that: Determining a corresponding service processing strategy according to the current time, and performing a corresponding service processing operation according to the service processing strategy, includes: When the current time is in the second time period, determining that the service processing strategy is a robot processing strategy; In the case where the service processing strategy is a robot processing strategy, the robot is controlled to move toward the user and output user greeting information.

5. The method according to claim 1, characterized in that Determining a corresponding service processing strategy according to the current time, and performing a corresponding service processing operation according to the service processing strategy, includes: When the current time is in the third time period, determining that the service processing strategy is a monitoring strategy; When the service processing strategy is a monitoring strategy, controlling the robot to move toward the user and acquiring an image of the user; The health status of the user is determined based on the image, and when the health status of the user is abnormal, a rescue request message is sent to a rescue platform, wherein the rescue request message includes the location of the user.

6. The method according to any one of claims 1 to 5, characterized in that: The extracting the voiceprint information of the user from the audio information includes: Determining the time-frequency masking of the speech signal in the audio information, and determining the power spectrum of the speech signal according to the time-frequency masking of the speech signal; Determining the time-frequency masking of the noise signal in the audio information, and determining the power spectrum of the noise signal according to the time-frequency masking of the noise signal; The speech signal is separated from the noise signal according to the power spectrum of the speech signal and the power spectrum of the noise signal, and the speech signal obtained by separation is enhanced to obtain the voiceprint information.

7. The method according to any one of claims 1 to 5, characterized in that: The identifying, according to the voiceprint information, whether the user is a historical user with a business handling record includes: Extracting voiceprint features from the voiceprint information; According to the voiceprint feature and the historical user voiceprint library, identifying whether the voiceprint information is voiceprint information in the historical user voiceprint library through a voiceprint recognition model, wherein the historical user voiceprint library includes voiceprint information of users with business handling records; In the case where the voiceprint information is the voiceprint information in the historical user voiceprint library, it is determined that the user is a historical user.

8. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Displaying a business processing record by a display device, the business processing record including the user, the current time and the progress of the business processing operation; In response to a completion instruction of the business processing operation, the business processing record corresponding to the business processing operation is deleted.

9. A service processing device, comprising: An extraction module, used to collect audio information of a user and extract the voiceprint information of the user from the audio information; An identification module, used to determine whether the user is a historical user with a business handling record according to the voiceprint information; The execution module is used to determine the corresponding business processing strategy according to the current time when the user is a historical user, and execute the corresponding business processing operation according to the business processing strategy.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images